[AMD][DI][CI] Auto-mount latest host ionic/ibverbs userspace in the MI355X nightly launcher (fix ABI mismatch) (#33374)

Co-authored-by: Chen <bingxche@amd.com>
2026-08-03 18:14:14 -07:00
parent 7f6a2e2b50
commit 03f44c978a
2 changed files with 34 additions and 7 deletions
@@ -145,10 +145,6 @@ jobs:
          # Manual dispatch input wins; otherwise use the latest image resolved
          # by the setup job; otherwise the launcher falls back to the recipe default.
          IMAGE_OVERRIDE: ${{ inputs.image != '' && inputs.image || needs.setup.outputs.image }}
-          # Keep the scheduler off mia1-p01-g20: its ionic RDMA driver ABI
-          # mismatches the container, so MORI reports "no active RDMA device"
-          # and the disagg server dies on init. Remove once the node is fixed.
-          SLURM_EXCLUDE: mia1-p01-g20
        run: bash scripts/ci/slurm/launch_mi355x.sh

      - name: Pack logs